DQN Algorithm for network resource management in vehicular communication network

To guarantee the effective utilization of time when users are stuck in network traffic congestion, it is necessary to train a reinforcement learning agent that tells those routes to users which have less network traffic congestion. The agents constantly engage with their surroundings and help user to find the best possible route. Every time agent gets the reward according to the choice of the user. For training an agent, we use DQN (Deep Q Network) which works on Q values. DQN agent gets the 345 rewards up to 500 iterations. Simulation results validate the effectiveness and efficiency of the DQN agent. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.